Methods and systems are presented for predicting a likelihood of an occurrence of an event, such as a dispute or a chargeback, associated with an electronic transaction based on monitoring user interactions of a user with one or more computing systems after the electronic transaction has been conducted. The electronic transaction may involve a purchase of a product and/or service from a merchant. After the transaction is conducted, user interactions of the user with the one or more computer systems, such as a website of the merchant involved in the transaction, a website of another merchant, and a website of a payment service provider may be monitored. A machine learning model may then be used to predict whether the event associated with the transaction will occur in the future based on the monitored user interactions.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A system, comprising: a non-transitory memory; and one or more hardware processors coupled with the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising: receiving an indication that a transaction has occurred between a user and a merchant, wherein the transaction comprises a purchase of an item from the merchant; monitoring interactions of the user with one or more computing systems over a period of time after the receiving of the indication; determining, using a machine learning model based on the monitored interactions, a likelihood that an event will be associated with the transaction, wherein the event comprises at least one of a dispute event or a chargeback event; determining an action associated with the event; determining the likelihood is higher than a predetermined threshold; performing the action for the user based on the likelihood being higher than the predetermined threshold; determining whether the event associated with the transaction has occurred; and training the machine learning model based on information indicating whether the event associated with the transaction has occurred.
2. The system of claim 1 , wherein the period of time is between the receiving of the indication and a settlement of the transaction.
3. The system of claim 1 , wherein the transaction occurred over a merchant interface associated with the merchant, wherein the monitoring the interactions comprises determining whether the user has browsed a particular page within the merchant interface during the period of time.
4. The system of claim 1 , wherein the merchant is a first merchant, wherein the transaction occurred over a first merchant interface associated with the first merchant, wherein the monitoring the interactions comprises monitoring interactions of the user with a second interface associated with a second merchant during the period of time.
5. The system of claim 1 , wherein the performing the action comprises: determining a shipment status related to shipping the item to the user; and transmitting the shipment status to a device associated with the user.
6. The system of claim 1 , wherein the operations further comprise transmitting the likelihood to a device associated with the merchant.
7. The system of claim 1 , wherein the operations further comprise: determining an elapsed amount of time between the receiving the indication and a shipment of the item, wherein the likelihood is determined further based on the elapsed amount of time.
8. The system of claim 1 , wherein the event comprises a chargeback event.
9. A method, comprising: receiving an indication that a transaction has occurred between a user and a merchant, wherein the transaction comprises a purchase of an item from the merchant; monitoring first user interactions of the user with one or more computing systems over a first period of time after receiving the indication; determining, by using a machine learning model based on the first user interactions, a first likelihood that a dispute event or a chargeback event associated with the transaction will occur; withholding funds associated with the transaction from the merchant based on the first likelihood; performing a remedial action for the user in response to the determining; determining a second likelihood that the dispute event or the chargeback event associated with the transaction will occur by using the machine learning model based on information obtained after the remedial action is performed; in response to determining that the second likelihood is below a predetermined threshold, releasing the funds to the merchant; determining whether the dispute event or the chargeback event associated with the transaction has occurred; and training the machine learning model based on information indicating whether the dispute event or the chargeback event associated with the transaction has occurred.
10. The method of claim 9 , further comprising monitoring second user interactions of the user with the one or more computing systems over a second period of time after performing the remedial action, wherein the second likelihood is determined by using the machine learning model based on the monitored second user interactions.
11. The method of claim 9 , wherein the performing the remedial action comprises: retrieving a shipment status from a server associated with a courier; and transmitting the shipment status to a user device associated with the user.
12. The method of claim 9 , further comprise providing a user interface to the merchant, wherein the user interface indicates that the funds associated with the transaction is withheld and includes an action selector that enables the merchant to select an action from a list of remedial actions, and wherein the remedial action is performed based on a selection by the merchant.
13. A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising: receiving an indication that a transaction has occurred between a user and a merchant, wherein the transaction comprises a purchase of an item from the merchant; monitoring interactions of the user with one or more computing systems over a period of time after the receiving of the indication; determining, using a machine learning model based on the monitored interactions, a likelihood that an event will be associated with the transaction, wherein the event comprises at least one of a dispute event or a chargeback event; in response to determining that the likelihood is higher than a predetermined threshold, performing an action for the user; determining whether the event associated with the transaction has occurred; and training the machine learning model based on information indicating whether the event associated with the transaction has occurred.
14. The non-transitory machine-readable medium of claim 13 , wherein the interactions are monitored during the period of time between the receiving of the indication and a settlement of the transaction.
15. The non-transitory machine-readable medium of claim 13 , wherein the transaction occurred over a merchant interface associated with the merchant, wherein the monitoring the interactions comprises determining whether the user has browsed a particular page within the merchant interface during the period of time.
16. The non-transitory machine-readable medium of claim 13 , wherein the merchant is a first merchant, wherein the transaction occurred over a first merchant interface associated with the first merchant, wherein the monitoring the interactions comprises monitoring interactions of the user with a second interface associated with a second merchant during the period of time.
17. The non-transitory machine-readable medium of claim 13 , wherein the performing the action comprises: determining a shipment status related to shipping the item to the user; and transmitting the shipment status to a device associated with the user.
18. The non-transitory machine-readable medium of claim 13 , wherein the operations further comprise transmitting the likelihood to a device associated with the merchant.
19. The non-transitory machine-readable medium of claim 13 , wherein the operations further comprise: determining an elapsed amount of time between the receiving the indication and a shipment of the item, wherein the likelihood is determined further based on the elapsed amount of time.
20. The non-transitory machine-readable medium of claim 13 , wherein the event comprises a transaction dispute event.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
April 4, 2019
March 30, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.